AI 导读
ScaleDown 推出 Constrained Decoding Models（CDM），一次读取输入后直接指向答案，跳过逐 token 生成，提供 Classify、Extract、Summarize 三款模型。支持 1M token 的文本加图像输入，DecisionBench 得分 77.2%，官方称比前沿 LLM API 快 200 倍、便宜 467 倍，输入价格 $0.05/M tokens 且输出免费，已在 OpenRouter、LangChain 等平台上线。
正文
1M-token, multimodal decision models are here!
But there is more to this one.
You can classify, extract, and summarize with 1M tokens of text and image input.
ScaleDown's Constrained Decoding Models read the input once and point straight to the answer, with no token-by-token generation.
200x faster, 467x cheaper than frontier LLM APIs.
You already gave the LLM the answer. So why is it writing it out from scratch? Introducing a new AI model architecture: Constrained Decoding Models (CDMs) LLMs were built to write. Most production workloads just need an answer: fast, consistent, and affordable. CDMs are purpose-built for 1 task each. They read your input once and skip the token-by-token generative loop that makes LLMs slow and expensive. Not just a decision model, but a family of 3 CDMs live today: • Classify: define your labels and get back a calibrated probability + reason for each. Used for routing, tagging, and intent detection. • Extract: describe the entities in natural language and get back well-formed JSON with confidence scores + citations. Used for web scraping, document processing, and PII redaction. • Summarize: pass in long text, images, or PDFs and get back a consistent summary under 1,000 tokens. Used for context compaction, metadata generation, and transcript digests. Built for production: • 1M tokens of multimodal (text + image) input, 31x larger than Jev • 77.2% on DecisionBench vs Jev's 72% • 200x faster, 467x cheaper than frontier LLM APIs • $0.05/M input tokens. Output is free (yes, even for summarize) Live on your favorite platforms today: @OpenRouter @vercel_dev @LiteLLM @LangChain @TrustedRouter @itsArthurAI @useRouterPlus Get 50M input tokens for free (for the first 50 hours) at link below 👀在 X 查看被引用的帖子
来源：elvis · x.com